pionex-earn-dual

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @pionex/pionex-ai-kit Node.js package to provide its core functionality. This is a vendor-provided package matching the author's identity.
  • [COMMAND_EXECUTION]: The skill utilizes the pionex-trade-cli and pionex-ai-kit binaries to execute both read and write operations on the Pionex platform. This includes account onboarding, market data retrieval, and financial transactions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, such as product listings and price feeds, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through command outputs from pionex-trade-cli earn dual open_products, prices, and get_invests in SKILL.md.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The skill has the capability to execute shell commands (pionex-trade-cli) and perform write operations on financial accounts.
  • Sanitization: No explicit sanitization or validation of the API-provided strings is described in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:38 PM
Security Audit — agent-trust-hub — pionex-earn-dual